evaluate_model: Construct and evaluate a ligand-target model given input...

In saeyslab/nichenetr: NicheNet: Modeling Intercellular Communication by Linking Ligands to Target Genes

Construct and evaluate a ligand-target model given input parameters.

Description

evaluate_model will take as input a setting of parameters (data source weights and hyperparameters) and layer-specific networks to construct a ligand-target matrix and evaluate its performance on input validation settings (both target gene prediction and ligand activity prediction).

Usage

evaluate_model(parameters_setting, lr_network, sig_network, gr_network, settings, calculate_popularity_bias_target_prediction,calculate_popularity_bias_ligand_prediction, ncitations = ncitations, secondary_targets = FALSE, remove_direct_links = "no", n_target_bins = 3,...)

Arguments

parameters_setting	A list containing following elements: $model_name, $source_weights, $lr_sig_hub, $gr_hub, $ltf_cutoff, $algorithm, $damping_factor, $correct_topology. See prepare_settings_leave_one_in_characterization and add_hyperparameters_parameter_settings.
lr_network	A data frame / tibble containing ligand-receptor interactions (required columns: from, to, source)
sig_network	A data frame / tibble containing signaling interactions (required columns: from, to, source)
gr_network	A data frame / tibble containing gene regulatory interactions (required columns: from, to, source)
settings	A list of lists for which each sub-list contains the following elements: .$name: name of the setting; .$from: name(s) of the ligand(s) active in the setting of interest; .$response: named logical vector indicating whether a target is a TRUE target of the possibly active ligand(s) or a FALSE.
calculate_popularity_bias_target_prediction	Indicate whether popularity bias in target gene prediction performance should be calculated (TRUE or FALSE).
calculate_popularity_bias_ligand_prediction	Indicate whether popularity bias in ligand activity prediction performance should be calculated (TRUE or FALSE).
ncitations	A data frame denoting the number of times a gene is mentioned in the Pubmed literature. Should at least contain following variables: 'symbol' and 'ncitations'. Default: ncitations (variable contained in this package). See function get_ncitations_genes for a function that makes this data frame from current Pubmed information.
secondary_targets	Indicate whether a ligand-target matrix should be returned that explicitly includes putative secondary targets of a ligand (by means of an additional matrix multiplication step considering primary targets as possible regulators). Default: FALSE
remove_direct_links	Indicate whether direct ligand-target and receptor-target links in the gene regulatory network should be kept or not. "no": keep links; "ligand": remove direct ligand-target links; "ligand-receptor": remove both direct ligand-target and receptor-target links. Default: "no"
n_target_bins	Indicate the number of bins the target genes will be divided in according to popularity. Only relevant when calculate_popularity_bias_target_prediction and/or calculate_popularity_bias_ligand_prediction is/are TRUE. Default = 3.
...	Additional arguments to make_discrete_ligand_target_matrix.

Value

A list containing following elements: $model_name, $performances_target_prediction, $performances_ligand_prediction, $performances_ligand_prediction_single

Examples

## Not run: 
library(dplyr)
settings = lapply(expression_settings_validation[1:4], convert_expression_settings_evaluation)
weights_settings_loi = prepare_settings_leave_one_in_characterization(lr_network,sig_network, gr_network, source_weights_df)
weights_settings_loi = lapply(weights_settings_loi,add_hyperparameters_parameter_settings, lr_sig_hub = 0.25,gr_hub = 0.5,ltf_cutoff = 0,algorithm = "PPR",damping_factor = 0.8,correct_topology = TRUE)
doMC::registerDoMC(cores = 8)
output_characterization = parallel::mclapply(weights_settings_loi[1:3],evaluate_model,lr_network,sig_network, gr_network,settings,calculate_popularity_bias_target_prediction = TRUE, calculate_popularity_bias_ligand_prediction = TRUE, ncitations, mc.cores = 3)

## End(Not run)

saeyslab/nichenetr documentation built on March 26, 2024, 9:22 a.m.